# ERM-MinMaxGAP: Benchmarking and Mitigating Gender Bias in Multilingual Multimodal Speech-LLM Emotion Recognition

arXiv: https://arxiv.org/abs/2603.21050 · HTML: https://mlsanity.com/paper/2603.21050/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2026.

## Built on by (most cited first, 2 of 2)

- [Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models](https://mlsanity.com/paper/2609.09263/) (2026)
- [EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis](https://mlsanity.com/paper/2608.23758/) (2026)

## Abstract (arXiv)

Speech emotion recognition (SER) systems can exhibit gender-related performance disparities, but how such bias manifests in multilingual speech LLMs across languages and modalities is unclear. We introduce a novel multilingual, multimodal benchmark built on MELD-ST, spanning English, Japanese, and German, to quantify language-specific SER performance and gender gaps. We find bias is strongly language-dependent, and multimodal fusion does not reliably improve fairness. To address these, we propose ERM-MinMaxGAP, a fairness-informed training objective, which augments empirical risk minimization (ERM) with a proposed adaptive fairness weight mechanism and a novel MinMaxGAP regularizer on the maximum male-female loss gap within each language and modality. Building upon the Qwen2-Audio backbone, our ERM-MinMaxGAP approach improves multilingual SER performance by 5.5% and 5.0% while reducing the overall gender bias gap by 0.1% and 1.4% in the unimodal and multimodal settings, respectively.